News for hackers. Stuff that matters.
Re:Show HN: Summate.it – Quickly summarize web articles with... by cloudking on Tuesday January 17, 2023 @09:14PM (#34422618)
Agreed, you can try sending it in chunks but then you lose context. Perhaps the ChatGPT based API will help if they expose the conversational memory as a feature.

Maybe OP has figured out a method with the current API?

Re:Show HN: Summate.it – Quickly summarize web articles with... by k1m on Tuesday January 17, 2023 @09:20PM (#34422659)
This is an issue. I haven't experimented to see if there are workarounds, so the service currently checks the length of the article text and if it's very long, it will send a portion, otherwise we'll exceed the token limit. There's a note on the front page about it: "Limitations: The OpenAI API does not allow submission of large texts, so summarization may only be based on a portion of the whole article."
Re:Show HN: Summate.it – Quickly summarize web articles with... by peytoncasper on Tuesday January 17, 2023 @09:19PM (#34422653)
I saw in another thread that people were working around this by asking for a summary of sections and then combining the summaries and asking for a joint summary.

Kind of like map reducing the articles.

Re:Show HN: Summate.it – Quickly summarize web articles with... by sudoelefant on Tuesday January 17, 2023 @09:57PM (#34422912)
O believe this is how GPT-Index attempts to bypass prompt length limitations.
Re:Show HN: Summate.it – Quickly summarize web articles with... by roflyear on Tuesday January 17, 2023 @10:21PM (#34423068)
ChatGPT doesn't seem to have a much longer memory
Re:Show HN: Summate.it – Quickly summarize web articles with... by gamegoblin on Wednesday January 18, 2023 @12:56AM (#34423848)
It's 2x the length of GPT3. 8192 tokens vs 4096.
Re:Show HN: Summate.it – Quickly summarize web articles with... by ijidak on Tuesday January 17, 2023 @10:22PM (#34423073)
Not promoting this. But, sounds like a great area for monetization.

Anyone can use without conversational memory, or with limited conversational memory.

Then, charge for larger conversational memory.